© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 88095
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    NECT
    -0.26
    å¾Ģå¹´
    -0.26
    ='_
    -0.26
    $_['
    -0.25
    AMPL
    -0.25
    æĪĽ
    -0.25
    hof
    -0.24
    orne
    -0.24
    ampling
    -0.24
    ound
    -0.24
    POSITIVE LOGITS
    é¦Ļåij³
    0.28
    KT
    0.28
    .locale
    0.26
    åijĥ
    0.26
    ä¾
    0.25
    uars
    0.25
    leon
    0.25
     barring
    0.25
     ap
    0.24
    -bre
    0.24
    Activations Density 6.552%

    No Known Activations

    This feature has no known activations.